mlsanityData to 7 Oct 2026

Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment

arXiv 2401.12474 ↗First posted 23 Jan 2024cs.CL cs.LGcited by 104

Not on the map. Why?

Cited by 21 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Considerable efforts have been invested in augmenting the role-playing proficiency of open-source large language models (LLMs) by emulating proprietary counterparts. Nevertheless, we posit that LLMs inherently harbor role-play capabilities, owing to the extensive knowledge of characters and potential dialogues ingrained in their vast training corpora. Thus, in this study, we introduce Ditto, a self-alignment method for role-play. Ditto capitalizes on character knowledge, encouraging an instruction-following LLM to simulate role-play dialogues as a variant of reading comprehension. This method creates a role-play training set comprising 4,000 characters, surpassing the scale of currently available datasets by tenfold regarding the number of roles. Subsequently, we fine-tune the LLM using this self-generated dataset to augment its role-playing capabilities. Upon evaluating our meticulously constructed and reproducible role-play benchmark and the roleplay subset of MT-Bench, Ditto, in various parameter scales, consistently maintains a consistent role identity and provides accurate role-specific knowledge in multi-turn role-play conversations. Notably, it outperforms all open-source role-play baselines, showcasing performance levels comparable to advanced proprietary chatbots. Furthermore, we present the first comprehensive cross-supervision alignment experiment in the role-play domain, revealing that the intrinsic capabilities of LLMs confine the knowledge within role-play. Meanwhile, the role-play styles can be easily acquired with the guidance of smaller models. We open-source related resources at https://github.com/OFA-Sys/Ditto.

Key facts. Cited by 104 papers in the map (data through 7 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 23 Jan 2024.

Builds on

11 of 21 references.

References · 11

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Qwen Technical Reportcited by 3,273
  5. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  6. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  7. 2023The False Promise of Imitating Proprietary LLMscited by 254
  8. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 250
  9. 2023Wider and Deeper LLM Networks are Fairer LLM Evaluatorscited by 91
  10. 2023CharacterChat: Learning towards Conversational AI with Personalized Social Supportcited by 58
  11. 2020Coarse-to-Fine Pre-training for Named Entity Recognitioncited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 41; 2025: 41; 2026: 22.

104 papers.

Sort:

By area:

  1. 2024Qwen2.5 Technical Reportcited by 4,713
  2. 2024Qwen2 Technical Reportcited by 2,076
  3. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  4. 2024A Survey on Self-Evolution of Large Language Modelscited by 86
  5. 2024PERSONA: A Reproducible Testbed for Pluralistic Alignmentcited by 71
  6. 2024The Oscars of AI Theater: A Survey on Role-Playing with Language Modelscited by 47
  7. 2024From Role-Play to Drama-Interaction: An LLM Solutioncited by 42
  8. 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoningcited by 40
  9. 2025Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profilescited by 38
  10. 2024IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generationcited by 35
  11. 2024AI Safety in Generative AI Large Language Models: A Surveycited by 31
  12. 2025SDPO: Segment-Level Direct Preference Optimization for Social Agentscited by 29
38 more
  1. 2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learningcited by 27
  2. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrievalcited by 26
  3. 2025CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulationcited by 26
  4. 2025OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personascited by 25
  5. 2024SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agentcited by 24
  6. 2025Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMscited by 22
  7. 2024TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Modelscited by 21
  8. 2025AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulationcited by 21
  9. 2025Population-Aligned Persona Generation for LLM-based Social Simulationcited by 20
  10. 2024RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systemscited by 19
  11. 2024Mitigating Hallucination in Fictional Character Role-Playcited by 17
  12. 2024Self-Cognition in Large Language Models: An Exploratory Studycited by 14
  13. 2026A Survey on LLM-based Conversational User Simulationcited by 14
  14. 2024BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Modelcited by 13
  15. 2024Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Modelscited by 13
  16. 2025NarraBench: A Comprehensive Framework for Narrative Benchmarkingcited by 13
  17. 2025Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactionscited by 12
  18. 2024The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trendscited by 11
  19. 2024Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Frameworkcited by 10
  20. 2024PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluationcited by 10
  21. 2025RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playingcited by 10
  22. 2025CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimizationcited by 10
  23. 2024Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playingcited by 9
  24. 2025Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMscited by 9
  25. 2025Towards Enhanced Immersion and Agency for LLM-based Interactive Dramacited by 9
  26. 2025PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?cited by 9
  27. 2025Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agentscited by 8
  28. 2024ChatGPT Role-play Dataset: Analysis of User Motives and Model Naturalnesscited by 7
  29. 2024Who Speaks Next? Multi-party AI Discussion Leveraging the Systematics of Turn-taking in Murder Mystery Gamescited by 7
  30. 2025The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agentscited by 7
  31. 2025Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy Planningcited by 7
  32. 2025RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrievalcited by 7
  33. 2025RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV Swarmscited by 7
  34. 2025HyCoRA: Hyper-Contrastive Role-Adaptive Learning for Role-Playingcited by 7
  35. 2026Reward Modeling from Natural Language Human Feedbackcited by 7
  36. 2024X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agentscited by 6
  37. 2024A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Stylescited by 6
  38. 2024DEMO: Reframing Dialogue Interaction with Fine-grained Element Modelingcited by 6

50 most cited of 104 All 104 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following
  2. 2026Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models
  3. 2025Reasoning Does Not Necessarily Improve Role-Playing Ability
  4. 2025Improving LLM Reasoning through Interpretable Role-Playing Steering
  5. 2023Better Zero-Shot Reasoning with Role-Play Prompting
  6. 2026OSPD: On-Policy Self-Distillation for Persona-Consistent Dialogue
  7. 2025SpeechRole: A Large-Scale Dataset and Benchmark for Evaluating Speech Role-Playing Agents
  8. 2023RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models